Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (4): 820-826    DOI: 10.11873/j.issn.1004-0323.2021.4.0820
遥感应用     
一种基于噪声水平估计的扩展线性光谱分解算法
段金亮1(),张瑞1,2(),李奎1,庞家泰1
1.西南交通大学 地球科学与环境工程学院测绘遥感信息系,四川 成都 611756
2.西南交通大学 高速铁路运营安全空间信息技术国家地方联合工程实验室,四川 成都 611756
A Kind of Extended Linear Spectral Unmixing Algorithm based on Noise Level Estimation
Jinliang Duan1(),Rui Zhang1,2(),Kui Li1,Jiatai Pang1
1.Faculty of Geosciences and Environmental Engineering,Southwest JiaotongUniversity,Chengdu 611756,China
2.State-Province Joint Engineering Laboratory of Spatial Information Technology of High-Speed Rail Safety,Chengdu 611756,China
 全文: PDF(3893 KB)   HTML
摘要:

针对传统的光谱分解算法忽略了影像在不同波段的不同噪声水平,导致分解精度提高受限。为克服这个问题,以高光谱影像为基础,提出了一种基于噪声水平估计的扩展线性光谱分解算法(NELMM)。首先,根据高光谱应用中的多元回归理论,估计相邻波段的噪声;其次,从估计噪声中获得噪声权重矩阵;最后,将噪声权重矩阵引入到线性混合像元的框架中,可以减轻不同波段噪声水平的影响。为验证算法精度,利用全约束最小二乘法(FCLS)和协同稀疏分解算法(CLSUnSAL)来进行对比分析,并通过此算法反演TM影像的植被覆盖度来验证其在多光谱影像上的实用性。结果表明:NELMM算法对高光谱影像分解的结果比FCLS和CLSUnSAL好,其噪声权重矩阵很好地平衡了波段间的噪声,使NELMM算法分解影像的精度显著提高;同时,此算法对多光谱影像分解呈现很好的适用性。

关键词: 高光谱影像植被覆盖度噪声权重矩阵多光谱影像扩展线性光谱分解    
Abstract:

The traditional spectralunmixing algorithm ignores the different noise levels of the image in different bands, which leads to the limited accuracy of unmixing. To overcome this problem, based on the hyperspectral imagery, an Extended linear spectral unmixing algorithm based on noise level estimation (NELMM) is proposed. First, according to the multivariate regression theory in hyperspectral applications, the noise in adjacent bands is estimated. Second, the noise weight matrix is obtained from the estimated noise. Finally,the noise weighting matrix is integrated into the linear spectral unmixing framework, which can alleviate the impact of different noise levels at different bands. In order to verify the accuracy of the algorithm, the Fully Constrained Least Squares (FCLS) and Collaborative Sparse Unmixing by variable Splitting and Augmented Lagrangian(CLSUnSAL) are used for comparative analysis, and the vegetation coverage of the TM image is inverted by this algorithm to verify its practicality on multispectral images. The final test results show that the NELMM algorithm is better than the FCLS and CLSUnSAL for the unmixing of hyperspectral images. The noise weight matrix balances the noise between the bands, and the accuracy of the NELMM algorithm for unmixing images is significantly improved. At the same time, this algorithm shows good applicability to multi-spectral image unmixing.

Key words: Hyperspectral image    Vegetation coverage    Noise Weight Matrix    ALI image    Extended Linear Spectral Unmixing
收稿日期: 2020-05-10 出版日期: 2021-09-26
ZTFLH:  TP75  
基金资助: 高分辨率对地观测重大专项航空观测系统(30?H30C01?9004?19/21);四川省科技计划(2018JY0564)
通讯作者: 张瑞     E-mail: jinliangduan@my.swjtu.edu.cn;zhangrui@swjtu.edu.cn
作者简介: 段金亮(1994-),男,四川达州人,硕士研究生,主要从事数字图像处理、定量遥感和光谱分解等研究。E?mail:jinliangduan@my.swjtu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
段金亮
张瑞
李奎
庞家泰

引用本文:

段金亮,张瑞,李奎,庞家泰. 一种基于噪声水平估计的扩展线性光谱分解算法[J]. 遥感技术与应用, 2021, 36(4): 820-826.

Jinliang Duan,Rui Zhang,Kui Li,Jiatai Pang. A Kind of Extended Linear Spectral Unmixing Algorithm based on Noise Level Estimation. Remote Sensing Technology and Application, 2021, 36(4): 820-826.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.4.0820        http://www.rsta.ac.cn/CN/Y2021/V36/I4/820

影像类型时间云量空间分辨率/m
Hyperion影像2006.07.180~9%30
ALI影像2006.07.180~9%10/30
TM影像2001.08.290.0730
ALI影像2001.08.2710%~19%10/30
表1  研究区影像的信息
图1  焉耆盆地的Hyperion影像和ALI影像
  图2玛纳斯的TM影像和ALI影像
图3  Hyperion影像的端元光谱库
图4  TM影像的植被端元光谱库
图5  FCLS、CLSUnSAL和NELMM的分解Hyperion影像的结果
指标RRMSE
类别12341234
FCLS0.77420.74010.75270.54550.26920.23370.23570.1701
CLSUnSAL0.78320.74760.75890.54660.26050.22760.22820.1637
NELMM0.81390.81930.82180.56740.21570.20680.18170.1420
表2  FCLS、CLSUNAL和NELMM分解Hyperion影像指标对比
图6  焉耆盆地的地表真实覆盖度
图7  玛纳斯地区的植被覆盖度
1 Williams M D, Parody R J, Fafard A J, et al. Validation of abundance map reference data for spectral unmixing[J].Remote Sensing, 2017, 9:473.DOI: 10.3390/rs9050473.
doi: 10.3390/rs9050473
2 Fan H, Chen Y, Guo Y, et al. Hyperspectral image restoration using low-rank tensor recovery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2017, 10:4589-4604.
3 Li Y, Huang X, Liu H. Unsupervised deep-feature learning for urban village detection from high-resolution remote sensing images[J]. Photogrammetric Engineering and Remote Sensing. 2017, 83: 567-579.
4 Bioucas-Dias J M, Plaza A, Dobigeon N, et al. Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches[J]. IEEE Journal afSelected Topics in Applied Earth Observations and Remote Sensing. 2012, 5:354-379.
5 Liu R, Du B, Zhang L. Hyperspectral unmixing via double abundance characteristics constraints based NMF[J]. Remote Sensing. 2016, 8: 464.DOI: 10.3390/rs8060464.
doi: 10.3390/rs8060464
6 Li C, Ma Y, Huang J, et al. GBM-Based Unmixing of hyperspectral data using bound projected optimal gradient method[J]. IEEE Transactions on Geoscience and Remote Sensing. 2016, 13:952-956.
7 Li Chang. Rsesarch on key technologies of hyperspectral remote sensing imagery[D]. Wuhan:Huazhong University of Science and Technology, 2018.
7 李畅. 高光谱遥感影像处理中的若干关键技术研究[D].武汉:华中科技大学,2018.
8 Heinz D C, Chang C I. Fully constrained ceast squares linear spectral mixture analysis method for material quantfication in Hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39:529-545.
9 Nascimento J M, Dias J M. Vertex component analysis: a fast algorithm to unmix Hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43:898-910.
10 Nascimento J M, Dias J M. Does Independent component analysis play a role in unmixing Hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43: 175-187.
11 Pauca V P, Piper J, Plemmons R J. Nonnegative matrix factorization for spectral data analysis[J]. Linear Algebra and Its Applications, 2006, 416: 29-47.
12 Ma J, Jiang J, Liu C, et al. Feature guided Gaussian mixture model with semi-supervised EM and local geometric constraint for retinal image registration[J]. Information Sciences, 2017, 417:128-142.
13 Akhtar N, Shafait F, Mian A. Futuristic greedy approach to sparse unmixing of hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53: 2157-2174.
14 Zhang G, Xu Y, Fang F. Framelet-based sparse unmixing of Hyperspectral images[J]. IEEE Transactions on Image Processing, 2016, 25:1516-1529.
15 Iordache M D, Bioucas-Dias J M, Plaza A. Total variation spatial regularization for sparse Hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50: 4484-4502.
16 Iordache M D, Bioucas-Dias J M, Plaza A. Collaborative sparse regression for Hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing,2014,52:341-354.
17 Bioucas-Dias J M, Nascimento J M. Hyperspectral subspace identification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46:2435-2445.
18 Zhang Yunxia, Li Xiaobing, Chen Yunhao. Overview of field and multiscale remote sensing measurement approaches to grassland vegetation coverage[J]. Advance In Earth Sciences, 2003,18(1):85-93.
18 张云霞,李晓兵,陈云浩.草地植被盖度的多尺度遥感与实地测量方法综述[J].地球科学进展,2003,18(1):85-93.
19 Xiao Hao,Wang Jie.Comparison between two spectral mixture analysis methods based on IDL and MATLAB[J].Remote Sensing Technology and Application,2017,32(5):858-865.
19 肖昊,王杰.基于IDL和MATLAB混合编程的两种光谱混合分析方法比较[J].遥感技术与应用,2017,32(5):858-865.
20 Uss M L, Vozel B, Lukin V V, et al. Local signal-dependent noise variance estimation from hyperspectral textural images[J]. IEEE Journal of Selected Topics in Signal Processing, 2011,5:469-486.
21 Duan Jinliang, Wang Jie,Wen Xingyue. Comparison analysis between two spectral mixture analysis methods of incorporating endmember variability[J]. Resource Development and Market, 2017, 33(6):651-655.
21 段金亮,王杰,文星跃. 基于端元变化的两种混合像元分解算法比较研究[J].资源开发与市场,2017,33(6):651-655.
22 Shi Ruihua, Li Xia, Dong Xinguang, et al. Research on the relationship between natural vegetation growth and groundwater in Yanqi basin[J]. Journal of Natural Resources, 2009, 24(12):2096-2103.
22 石瑞花,李霞,董新光等.焉耆盆地天然植被与地下水关系研究[J].自然资源学报, 2009, 24(12):2096-2103.
23 Duan Jinliang, Wang Jie, Zhang Ting. A kind of vegetation cover fraction retrieval algorithm based on spectral normalization frame[J]. Remote Sensing Technology and Application, 2018, 33(2): 252-258.
23 段金亮,王杰,张婷.一种基于光谱归一化下的植被覆盖度反演算法[J].遥感技术与应用,2018,33(2):252-258.
24 Chander G, Markham B L, Helder D L. Summary of current radiometric calibration coefficients for Landsat MSS, TM, ETM+, and EO-1 ALI sensors[J]. Remote Sensing of Environment, 2009, 113(5):893-903.
25 Wang Jie,YangLiao,ShenJinxiang, et al. Two endmember extraction algorithms with combined spatial and spectral domain TM image[J], Spectroscopy and Spectral Analysis, 2011,31(5):1286-1290.
25 王杰,杨辽,沈金祥,等.两种基于空间与光谱相结合的TM影像端元提取算法[J]. 光谱学与光谱分析,2011,31(5):1286-1290.
26 Veganzones M A, Drumetz L, Tochon G, et al. A new extended linear mixing model to address spectral variability[C]∥ Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2014, 6(6):1-5
27 Xinyu W, Yanfei Z, Liangpei Z, et al. Spatial group sparsity regularized nonnegative matrix factorization for Hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55: 6287-6304.
[1] 林志垒,张贵成. 基于改进Brovey变换的ALI影像融合算法研究[J]. 遥感技术与应用, 2020, 35(4): 893-900.
[2] 龙爽,郭正飞,徐粒,周华真,方伟华,许映军. 基于Google Earth Engine的中国植被覆盖度时空变化特征分析[J]. 遥感技术与应用, 2020, 35(2): 326-334.
[3] 谭美宝,冉有华,苏阳,李新,杜得彦,廉耀康. 黑河流域2001~2017年植被变化特征及其可延续性评价[J]. 遥感技术与应用, 2020, 35(2): 335-344.
[4] 李哲, 宫兆宁, 刘先林, 关晖, 王颖. 基于面向对象多端元混解模型的植被覆盖度反演及其时空分布研究[J]. 遥感技术与应用, 2018, 33(6): 1149-1158.
[5] 孙红, 田昕, 闫敏, 李增元, 陈尔学, 孙珊珊, 王崇阳. 内蒙古大兴安岭根河植被覆盖度动态变化及影响因素的分析[J]. 遥感技术与应用, 2018, 33(6): 1159-1169.
[6] 段金亮,王杰,张婷. 一种基于光谱归一化下的植被覆盖度反演算法[J]. 遥感技术与应用, 2018, 33(2): 252-258.
[7] 肖昊,王杰. 基于IDL和MATLAB混合编程的两种光谱混合分析方法比较[J]. 遥感技术与应用, 2017, 32(5): 858-865.
[8] 方雨晨,王培燕,田庆久. 不同覆盖度下小麦农田土壤对NDVI影响模拟分析[J]. 遥感技术与应用, 2017, 32(4): 660-666.
[9] 周在明,杨燕明,陈本清. 基于无人机影像的滩涂入侵种互花米草植被信息提取与覆盖度研究[J]. 遥感技术与应用, 2017, 32(4): 714-720.
[10] 李恒凯,欧彬,刘雨婷,邱玉宝. 基于混合像元分解的高光谱影像柑橘识别方法[J]. 遥感技术与应用, 2017, 32(4): 743-750.
[11] 吴志杰,何国金,王猛猛,傅娇凤,邹丹. 南方丘陵区植被覆盖度遥感估算与时空变化研究—以福建省永定县为例[J]. 遥感技术与应用, 2016, 31(6): 1201-1208.
[12] 鲍蕊,夏俊士,薛朝辉,杜培军,车美琴. 基于形态学属性剖面的高光谱影像集成分类[J]. 遥感技术与应用, 2016, 31(4): 731-738.
[13] 陈阳,范建容,张云,李胜,甘泉,应国伟,曹伟超. 多云雾地区高时空分辨率植被覆盖度构建方法研究[J]. 遥感技术与应用, 2016, 31(3): 518-529.
[14] 李艺梦,祁元,马明国. 基于Landsat8影像的额济纳荒漠绿洲植被覆盖度估算方法对比研究[J]. 遥感技术与应用, 2016, 31(3): 590-598.
[15] 林志垒,晏路明. 高光谱影像的BDT-SVM地物分类算法与应用[J]. 遥感技术与应用, 2016, 31(1): 177-185.